Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to various political leaders and government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´ãĤ¡
    -0.74
    ãĤ½
    -0.73
    Reviewer
    -0.73
    à¨
    -0.70
    ++++++++++++++++
    -0.69
    Ire
    -0.68
    ãĥĢ
    -0.65
    Tu
    -0.63
    docs
    -0.62
    natureconservancy
    -0.62
    POSITIVE LOGITS
     Jr
    0.94
    bey
    0.85
    steen
    0.83
     oversaw
    0.80
    enei
    0.79
    ovich
    0.78
     III
    0.76
     joked
    0.74
     toured
    0.74
    hler
    0.72
    Act Density 0.165%

    No Known Activations